ADPKD Patient Classification via Height-Adjusted Kidney Volume
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for classifying autosomal dominant polycystic kidney disease (ADPKD) patients are limited by the variability in disease progression and the inability of total kidney volume (TKV) to accurately predict renal function decline, making it challenging to select appropriate patients for clinical trials and therapies.
Innovation Solution
An imaging classification system using computed tomography (CT) and magnetic resonance (MR) images to categorize ADPKD patients into typical and atypical presentations, further stratified based on height-adjusted total kidney volume (HtTKV) and age, allowing for the identification of patients with rapid to very rapid disease progression and those unlikely to benefit from therapies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If total kidney volume (TKV) is used to monitor disease progression, then the potential to monitor disease progression and serve as endpoint in clinical trials is improved, but measurement precision and prediction accuracy deteriorate due to limitations in predicting renal function change
Solution Approach 1:
The patent segments ADPKD patients into distinct subclasses (1A-1E) based on imaging characteristics and disease progression patterns. This segmentation allows for more precise prediction of renal function decline by categorizing patients into groups with similar progression rates, thereby resolving the contradiction between using TKV for monitoring and maintaining prediction accuracy.
Solution Approach 2:
The patent introduces multiple parameters beyond total kidney volume, including height-adjusted TKV (HtTKV), cyst distribution patterns, and imaging-based phenotypes. These additional parameters enhance the predictive accuracy of renal function decline while maintaining the utility of TKV for disease progression monitoring.
2Loss of time
If new therapies are implemented when GFR starts to decline, then treatment timing is improved, but therapeutic effectiveness deteriorates because most irreversible damage has already occurred
Solution Approach 1:
The patent enables preliminary identification of patients at high risk for rapid disease progression through imaging classification and subclassification before significant renal function decline occurs. This allows clinicians to initiate therapies earlier in the disease course, potentially preventing or delaying irreversible damage while maintaining therapeutic effectiveness.
3Measurement precision
If imaging classification and subclassification are applied, then patient selection precision for clinical trials is improved, but device complexity and classification system complexity increase
Solution Approach 1:
The patent applies segmentation by dividing patients into main classes (typical vs. atypical) and further into subclasses (1A-1E) based on imaging characteristics. This hierarchical segmentation improves patient selection precision while organizing the complexity into manageable categories that can be systematically applied in clinical settings.
Solution Approach 2:
The patent applies local quality by using specific imaging features and phenotypic characteristics relevant to each patient subgroup. Rather than applying a single complex classification to all patients, the system tailors the classification approach to local patient characteristics, improving precision while managing overall system complexity.
Data Source
AI summary
An apparatus and computerized method of classifying a patient that has been previously diagnosed to have autosomal dominant polycystic kidney disease (ADPKD) includes providing a computing device having an input/output interface, one or more processors and a memory; receiving a total kidney volume (TKV), a patient height, and a patient age for the patient via the input/output interface; determining a height adjusted TKV (HtTKV) based on the total kidney volume and the patient height using the one or more processors; determining an ADPKD classification for the patient based on the height adjusted TKV and the patient age using the one or more processors; and providing the ADPKD classification for the patient via the input/output interface.